Knowledge catalogue
arXiv:2607.20145v1 Announce Type: cross Abstract: Full-parameter post-training of trillion-parameter-scale MoE models introduces substantial system-level challenges for large-scale distributed trainin
arXiv:2607.20216v1 Announce Type: cross Abstract: Malware analysis demands rapid interpretation of complex detonation reports spanning filesystem, network, and process behaviours. While large language
arXiv:2607.20062v1 Announce Type: new Abstract: We present Solar Open 2, a 250B-A15B Mixture-of-Experts language model built for long-horizon agentic tasks, scaled up from Solar Open 1 (Solar Open 100
arXiv:2607.19518v1 Announce Type: new Abstract: Sophisticated Inference is a variant of active inference often associated with recursive belief modeling and tree search. We argue that its central comp
arXiv:2607.19368v1 Announce Type: new Abstract: Long-prompt inference remains expensive because prefill attention scales quadratically with sequence length. We propose Spectral-LSH, a training-free pr
Prime Intellect Lab offers a streamlined, hosted reinforcement‑learning workflow that lets users customize the NVIDIA Nemotron 3 Nano in minutes. The process establishes a baseline, trains the model o
arXiv:2607.19361v1 Announce Type: cross Abstract: Most safety guardrails for large language models (LLMs) evaluate each prompt-response pair in isolation, which misses failures that arise only over a
arXiv:2607.20205v1 Announce Type: cross Abstract: Low-rank adaptation (LoRA) has become a widely used parameter-efficient fine-tuning method for large language models. Since different modules and laye
arXiv:2607.19364v1 Announce Type: new Abstract: Activation steering offers a lightweight alternative to fine-tuning for behavioral control of large language models, but SAE-based steering methods ofte
arXiv:2607.19385v1 Announce Type: new Abstract: This paper tackles the problem of stock ranking and portfolio construction under realistic investment settings by jointly modeling temporal dynamics and
arXiv:2607.16290v2 Announce Type: replace Abstract: Leading entries on the multi-task track of the 11th ABAW challenge rely on heavy ensembling, yet which member is worth adding to an already strong e
arXiv:2607.19901v1 Announce Type: new Abstract: Deep learning frameworks like nnU-Net achieve state-of-theart brain lesion segmentation performance but remain difficult to deploy in clinical research
arXiv:2607.19384v1 Announce Type: new Abstract: Real-world intelligent systems often require both distributed collaboration across data-isolated clients and continual adaptation to evolving tasks. Thi
arXiv:2607.18907v1 Announce Type: new Abstract: Instance-level artwork recognition requires matching a handheld visitor photograph to a specific work in a large museum collection. This is challenging
arXiv:2607.19608v1 Announce Type: new Abstract: Instruction tuning is meant to make language models follow user requests, yet it is unclear whether small models comply when an instruction conflicts wi
arXiv:2607.16741v2 Announce Type: replace Abstract: Burger et al. (2024) demonstrated that truth representations in large language models are universal across statement polarity but reside within a mu
arXiv:2607.20301v1 Announce Type: cross Abstract: Fine-tuning has been widely used to adapt large language models (LLMs) for domain-specific tasks. Parameter efficient fine-tuning (PEFT) methods such
Welcome to The Blueprint, a new feature where we highlight how Google Cloud customers are tackling unique and common challenges across industries using the latest AI and cloud technologies. We hope to
arXiv:2607.19433v1 Announce Type: new Abstract: The transition from stateless generative models in artificial intelligence to stateful, autonomous agents represents an architectural evolution that, wh
The first known runaway AI agent - or a very bad marketing stunt? Martin Alderson's commentary on the OpenAI accidental cyberattack against Hugging Face includes a couple of details I hadn't considere
The first router built for generative media is here. Runway launches AI model router as generative media gets crowded https://techcrunch.com/2026/07/23/runway-bets-on-ai-model-routing-as-generative-me
arXiv:2607.20265v1 Announce Type: cross Abstract: Large-scale pretrained language models such as T5 and BERT have demonstrated strong capabilities for generating structured knowledge. However, their p
arXiv:2607.19749v1 Announce Type: cross Abstract: Model-based reinforcement-learning agents of the DreamerV3 family forget catastrophically when trained on task sequences, even when an unbounded repla
arXiv:2607.18856v1 Announce Type: new Abstract: Continuous Thought Machines introduce an internal temporal dimension in which neuron-level histories and synchronization-derived representations evolve
arXiv:2509.24739v4 Announce Type: replace Abstract: Vision-Language Foundation Models (VLMs), trained on large-scale multimodal datasets, have driven significant advances in Artificial Intelligence (A
arXiv:2607.17191v2 Announce Type: replace Abstract: Human-like private chat requires more than fluent response generation: a system must preserve persona, relationship, memory, bounded knowledge, medi
arXiv:2607.20379v1 Announce Type: new Abstract: Natural-language autoencoders score explanations of hidden activations by reconstruction: an explanation is deemed faithful if the activation can be reg
TL;DR: Everyone says QLoRA past ~13B is dead on a 24GB card. I got the full 32B FLUX.2 dev transformer QLoRA-training resident on the GPU on a 7900 XTX under native ROCm on Windows (no ZLUDA, no CUDA
arXiv:2607.19383v1 Announce Type: cross Abstract: Pretrained generative foundation models cast forecasting as conditional generation from a learned predictive distribution and forecast unseen series z
arXiv:2607.19794v1 Announce Type: new Abstract: Production LLM-based financial sentiment analysis faces a structural cost trap: most queries are trivially classifiable, yet expensive cloud reasoners p
arXiv:2606.15265v2 Announce Type: replace Abstract: Congenital heart disease (CHD) refers to the abnormal anatomical structure caused by the abnormal development of the heart and great vessels during
arXiv:2607.20328v1 Announce Type: cross Abstract: This study empirically analyzed generative AI as an emerging discovery pathway to academic library resources. Utilizing web analytics from August 2023
arXiv:2607.19971v1 Announce Type: new Abstract: Accurate motion prediction of surrounding agents and safe motion planning are two closely coupled key tasks for social robot navigation in crowded envir
arXiv:2602.07643v2 Announce Type: replace Abstract: Foundation models have emerged as a transformative paradigm in 3D medical imaging, with the promise of unified quantitative analysis across diverse
arXiv:2607.19442v1 Announce Type: cross Abstract: Machine unlearning is commonly evaluated by matching a retrained oracle on trained probes. In a controlled nonce-fact testbed with a matched retrainin
What's Changed mlx update by @dhiltgen in #17332 model/parsers: finalize incomplete GLM tool calls by @dhiltgen in #17250 docs: update retirements by @mxyng in #17289 model: align Laguna with upstream
arXiv:2603.06210v2 Announce Type: replace-cross Abstract: 3D semantic occupancy prediction has become a crucial perception task for comprehensive scene understanding in autonomous driving. While recen
We built this experience based on feedback from early testers and physicians. With your permission, ChatGPT can use relevant context you’ve connected in Health across your conversations — to help you
arXiv:2607.19956v1 Announce Type: cross Abstract: Knowledge distillation (KD) is a standard approach for compressing sequence-to-sequence models, but its per-sample effects are rarely examined. On the
arXiv:2607.19967v1 Announce Type: cross Abstract: Shippers are beginning to delegate carrier selection to large language model (LLM) agents. We ask what such delegation does to a freight matching mark
arXiv:2603.03989v3 Announce Type: replace-cross Abstract: When visual evidence is ambiguous, vision models must decide how to interpret face-like patterns. Face pareidolia, the perception of faces in
arXiv:2601.06442v2 Announce Type: replace Abstract: Point Cloud-based Place Recognition (PCPR) demonstrates considerable potential in applications such as autonomous driving, robot localization and na
arXiv:2512.02473v2 Announce Type: replace-cross Abstract: Video world models have attracted significant attention for their ability to produce high-fidelity future visual observations conditioned on p
arXiv:2607.15330v2 Announce Type: replace Abstract: We present Xiaomi-Robotics-1, a foundational vision-language-action (VLA) model capable of (1) following diverse language instructions to perform a
OpenAI has released ChatGPT Voice for the desktop app, enabling users to control their computer and direct multiple agents running in ChatGPT Work or Codex using voice commands. The feature, powered b
Scientists today face challenges of extraordinary scale and complexity. From shaping and simulating the intricate dynamics of fusion plasma, to exploring the vast search space of new materials, to mak
Anthropic PBC will purchase up to 2 gigawatts’ worth of graphics cards from Advanced Micro Devices Inc. as part of a multibillion-dollar deal announced today. The partnership also has several other co
Are AI labs pelicanmaxxing? Excellent piece of work by Dylan Castillo, who took a deep-dive into the frequently pondered question of whether the AI labs have been deliberately training models to draw
Are there MBA programs teaching fear marketing yet We're partnering with @huggingface to investigate an unprecedented security incident. Cyber-capable OpenAI models compromised Hugging Face production
This is a surprisingly large real-world deployment: 'GovGPT' is part of Austria’s Public AI initiative, running on sovereign infrastructure (in their BRZ - federal datacenter) with Mistral open-weight
Authentic Details and Deep Knowledge are also major upgrades in this release. Together, they enable Qwen-Image-3.0 to make real breakthroughs in high-value productivity scenarios — newspaper PDFs, sho
Available today in the langchain-ai/langchain-skills repo: https://github.com/langchain-ai/langchain-skills 💻 Install in Codex or Claude Code, open the repo w/ the agent you want to evaluate, start wi
cuda: add sqrt_softplus in topk-moe for dsv4 (#25896) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCF
hexagon: check tensor type when reusing descriptors (#25968) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64)
mtmd : use align_corners for qwen3vl vision position embedding interpolation (#25781) The Qwen3-VL learned position embedding is interpolated to the runtime patch grid with the default bilinear+antial
Add support for Laguna XS.2 & M.1 (#25165) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCFramework Li
llama-arch: fix DeepSeek4 APE tensor op (#25945) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCFramew
cuda: GET_ROWS quants (#25962) cuda: add k-quant support to GET_ROWS Device-side embedding lookups require GET_ROWS to handle the k-quants used by common GGUF recipes (Q4_K_M stores token_embd as q6_K
webgpu : add CONV_2D_DW (depthwise conv2d) kernel (#25847) webgpu : add CONV_2D_DW (depthwise conv2d) kernel Implement GGML_OP_CONV_2D_DW for the WebGPU backend, ported from the Vulkan backend's conv2
ci : fix SYCL package shared library lookup (#25987) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCFr